Analysis of low-dimensional radio-frequency impedance-based cardio-synchronous waveforms for biometric authentication.

Over the past two decades, there have been a lot of advances in the field of pattern analyses for biomedical signals, which have helped in both medical diagnoses and in furthering our understanding of the human body. A relatively recent area of interest is the utility of biomedical signals in the field of biometrics, i.e., for user identification. Seminal work in this domain has already been done using electrocardiograph (ECG) signals. In this paper, we discuss our ongoing work in using a relatively recent modality of biomedical signals-a cardio-synchronous waveform measured using a Radio-Frequency Impedance-Interrogation (RFII) device for the purpose of user identification. Compared to an ECG setup, this device is noninvasive and measurements can be obtained easily and quickly. Here, we discuss the feasibility of reducing the dimensions of these signals by projecting onto various subspaces while still preserving interuser discriminating information. We compare the classification performance using classical dimensionality reduction methods such as principal component analysis (PCA), independent component analysis (ICA), random projections, with more recent techniques such as K-SVD-based dictionary learning. We also report the reconstruction accuracies in these subspaces. Our results show that the dimensionality of the measured signals can be reduced by 60 fold while maintaining high user identification rates.

Biometric identification of cardiosynchronous waveforms utilizing person specific continuous and discrete wavelet transform features.

In this paper we explore how a Radio Frequency Impedance Interrogation (RFII) signal may be used as a biometric feature. This could allow the identification of subjects in operational and potentially hostile environments. Features extracted from the continuous and discrete wavelet decompositions of the signal are investigated for biometric identification. In the former case, the most discriminative features in the wavelet space were extracted using a Fisher ratio metric. Comparisons in the wavelet space were done using the Euclidean distance measure. In the latter case, the signal was decomposed at various levels using different wavelet bases, in order to extract both low frequency and high frequency components. Comparisons at each decomposition level were performed using the same distance measure as before. The data set used consists of four subjects, each with a 15 minute RFII recording. The various data samples for our experiments, corresponding to a single heart beat duration, were extracted from these recordings. We achieve identification rates of up to 99% using the CWT approach and rates of up to 100% using the DWT approach. While the small size of the dataset limits the interpretation of these results, further work with larger datasets is expected to develop better algorithms for subject identification.